<font size=2 face="sans-serif">My understanding is (someone will correct
me if I'm wrong) ...</font><br><br><font size=2 face="sans-serif">GPFS does not have true deadlock detection.
As you say it has time outs. The argument is: As a practical
matter, it makes not much difference to a sysadmin or user -- if things
are gummed up "too long" they start to smell like a deadlock,
so we may as well intervene as though there were a true technical deadlock.</font><br><br><font size=2 face="sans-serif">A genuine true deadlock is a situation
where things are gummed up, there is no progress, and one can prove that
there will be no progress, no matter how long one waits.</font><br><font size=2 face="sans-serif">E.g. Classically, you have locked resource
A and I have locked resource B and now I decide I need resource A and I
am waiting indefinitely long for that. And you have decided you need
resouce B and you are waiting indefinitely for that. We are then
deadlocked. Deadlock can occur on a single node or over multiple
nodes. </font><br><br><font size=2 face="sans-serif"> Technically it may be possible
to execute a deadlock detection protocol that would identify cyclic, deadlocking
dependencies, but it was decided that, for GPFS, it would be more practical
to detect "very long waiters"...</font><br><br><br><font size=2 face="sans-serif"><br></font><br><font size=1 color=#5f5f5f face="sans-serif">From:
</font><font size=1 face="sans-serif">"Oesterlin, Robert"
<Robert.Oesterlin@nuance.com></font><br><br><br><font size=1 face="Helvetica">Some general thoughts on \u201cdeadlocks\u201d
and automated deadlock detection.</font><br><br><font size=1 face="Helvetica">I personally don\u2019t like the term \u201cdeadlock\u201d
as it implies a condition that won\u2019t ever resolve itself. In GPFS terms,
a deadlock is really a \u201clong RPC waiter\u201d over a certain threshold. RPCs
that wait on certain events can and do occur and they can take some time
to complete. This is not necessarily a condition that is a problem, but
you should be looking into them.</font><br><br><font size=1 face="Helvetica">GPFS does have automated deadlock detection
and collection, but in the early releases it was \u2026 well.. it\u2019s not very
\u201crobust\u201d. With later releases (4.2) it\u2019s MUCH better. I personally don\u2019t
rely on it because in larger clusters it can be too aggressive and depending
on what\u2019s really going on it can make things worse. This statement is
my opinion and it doesn\u2019t mean it\u2019s not a good thing to have. :-) </font><br><br><br><font size=2 face="sans-serif">...</font><BR>